Triple
T23806123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yishan |
E589712
|
entity |
| Predicate | roleDuringFirstOpiumWar |
P108011
|
FINISHED |
| Object | commander of Qing forces |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: commander of Qing forces | Statement: [Yishan, roleDuringFirstOpiumWar, commander of Qing forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleDuringFirstOpiumWar Context triple: [Yishan, roleDuringFirstOpiumWar, commander of Qing forces]
-
A.
roleDuringSecondSinoJapaneseWar
Indicates the specific role, position, or function an entity held or performed during the Second Sino-Japanese War.
-
B.
roleInManchuria
Indicates that an entity holds or held a specific role, position, or function in the context of Manchuria.
-
C.
roleAtBattleOfYaluRiver
Indicates the specific role, position, or function an entity held or performed during the Battle of the Yalu River.
-
D.
roleInMeijiRestoration
Indicates the specific part, function, or contribution an entity had in bringing about or shaping the Meiji Restoration.
-
E.
roleInWarOrConflict
chosen
Indicates the specific function, position, or involvement an entity has within a particular war or conflict.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e25d19fecc8190a5cf39bbb18d5d7f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c75206a88190b6e35da289471c27 |
completed | April 29, 2026, 8:54 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:56 p.m.